Instructions to use OpenTO/LDM_L with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use OpenTO/LDM_L with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("OpenTO/LDM_L", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
Improve model card for Optimize Any Topology (OAT)
#1
by nielsr HF Staff - opened
This PR significantly improves the model card for the Optimize Any Topology (OAT) model by:
- Adding the
pipeline_tag: text-to-imageto enhance discoverability, as the model generates structural layouts (images). - Specifying the
license: apache-2.0. - Adding the
datasets: OpenTO/OpenTOtag, linking to the relevant dataset used for training on the Hugging Face Hub. - Populating the model description with details from the paper abstract and GitHub README.
- Including direct links to the paper and the official GitHub repository.
- Providing information about the training process, data, and available pre-trained checkpoints.
- Adding a BibTeX citation for the paper.
These updates aim to make the model card more comprehensive and useful for the community.